Back in June, I wrote about some scale-up experiments that we conducted with SAP software on vSphere 4. That work focused on a single VM, so we decided to follow it up with a study of multiple VMs on a single server. Collaborating with IBM, we performed experiments to study the scale-out behavior of SAP software: using vSphere 4 to run multiple VMs on a 24-core IBM x3850 M2. We presented this joint work at VMworld 2009 (EA 1640), and have recently written a whitepaper that contains the results: ftp://ftp.software.ibm.com/eserver/benchmarks/wp_x3850M2_VMware_SAP_Scaling_112009.pdf
This new whitepaper highlights the fairness of scheduling in vSphere and the hardware features of the x3850 M2 that allowed us to run 12 concurrent 2vCPU VMs with excellent performance. In addition, we showed that a variety of choices of vCPU count and VM count are possible with very little impact on performance (see figure).
VMware recently published a whitepaper that demonstrates VMware vSphere 4’s excellent performance and scalability with SAP ERP software. The paper presents results of several experiments using VMware vSphere and SAP software with both the Microsoft Windows Server 2008 and SUSE Linux 10.2 operating systems.
First, vSphere’s support for nested page tables (AMD Rapid Virtual Indexing, and Intel Extended Page Tables) is shown to provide a 15-82% performance boost for SAP's most MMU-intensive memory models. Next, the paper presents a "scale-up" study, comparing n-way virtual machines to n-way physical machines (see figure); using an SAP application load test, vSphere supported up to 95% of the users achieved on physical machines. The paper also shows that vSphere maintains fairness during CPU overcommitment for an SAP workload and that a performance benefit can be realized when large pages are configured on the host and guest.
The results in the paper suggest that to run SAP in a virtual machine most efficiently, one should adopt the following best practices:
- Run with no more vCPUs than necessary.
- Use the newest processors (e.g., “AMD Opteron 2300/8300 Series” or “Intel Xeon 5500 Series”) to exploit vSphere's support of hardware nested page tables.
- Limit virtual machine size to fit within a NUMA node.
- Configure guest operating system and applications for large pages.
- If using a processor with hardware nested page tables (RVI or EPT) and Linux, choose the Std memory model
- If using a processor with hardware nested page tables (RVI or EPT) and Windows 2008, convenience should dictate the choice of memory model as it has only a minor effect on performance.
For more information on the experiments and how we arrive at these recommendations, we refer you to the full paper. For additional SAP information, please visit: http://www.vmware.com/sap.